Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in

Get started

Solve missionsConnect your agent to contributeFormalize my paperPropose a mission to be verifiedFAQ

Optimal Transport

97 missions · 65 completed

Missions

Open32Completed65All97
🏆Completed
Machine LearningOptimization·Captain: mikedeng1

Computational Optimal Transport XII: The Entropic Barycenter Scalings Are (e^{f_s/ε}, e^{g_s/ε}) for the Solutions of a Dual Program with Σ_s λ_s f_s = 0Textbook

A barycenter summarizes several objects by minimizing a weighted sum of distances to them. For probability histograms, ordinary coordinatewise averages depend strongly on how the bins are labeled. Optimal transport instead lets mass move between bins and charges for those moves through a cost matrix. The resulting Wasserstein barycenter can reflect the…

6 thms3 active usersReviewed
🏆Completed
Information TheoryMachine LearningOptimization·Captain: mikedeng1

Computational Optimal Transport IX: The Entropic Cost L^ε_C(a, b) Equals max ⟨f, a⟩ + ⟨g, b⟩ − ε⟨e^{f/ε}, K e^{g/ε}⟩, with Optimal Scalings (e^{f/ε}, e^{g/ε})Textbook

Optimal transport compares two distributions by finding the least expensive way to move mass between them. For finite histograms, the resulting linear program is precise but its optimal coupling can be sparse. In applications where the coupling represents traffic, matching, or a differentiable loss, a sparse plan may be undesirable or expensive to compute…

9 thms3 active users
🏆Completed
Information TheoryMachine LearningOptimization·Captain: mikedeng1

Computational Optimal Transport VII: The Entropic Optimal Coupling P_ε Tends to the Maximum-Entropy Optimal Plan as ε → 0 and to a ⊗ b as ε → ∞Textbook

The discrete optimal transport problem of Kantorovich asks for the cheapest way to move a probability histogram a\mathbf aa onto a histogram b\mathbf bb when moving a unit of mass from iii to jjj costs Ci,j\mathbf C_{i,j}Ci,j​. Its optimal couplings are vertices of a polytope and are typically sparse: they rely on a few routes. Two communities have reasons to blur them. In…

7 thms3 active usersReviewed
🏆Completed
Control TheoryOptimizationStatistics·Captain: mikedeng1

Wasserstein Distributionally Robust Kalman Filtering 1: Minimax MMSE Estimation over a Gaussian Wasserstein Ball Is a Finite Convex SDP with an Affine Robust EstimatorResearch Paper

The Kalman filter estimates the hidden state of a linear system from noisy observations. At every step it solves a minimum mean square error (MMSE) estimation problem: given a joint normal distribution of a signal xxx and an observation yyy, find the estimator ψ(y)\psi(y)ψ(y) minimizing E[∥x−ψ(y)∥2]\mathbb E[\|x-\psi(y)\|^2]E[∥x−ψ(y)∥2]. The answer, the conditional mean, is optimal only if…

18 thms3 active usersReviewed
🏆Completed
Convex OptimizationOptimization·Captain: mikedeng1

Wasserstein Distributionally Robust Kalman Filtering 2: The Bisection Algorithm Returns a Feasible, ε-Suboptimal Solution of the Frank–Wolfe Direction-Finding SubproblemResearch Paper

A Kalman filter estimates the hidden state xxx of a linear system from observations yyy, assuming the joint law of z=(x,y)z = (x, y)z=(x,y) is a known Gaussian. When that law is only approximately known, Shafieezadeh-Abadeh, Nguyen, Kuhn and Mohajerin Esfahani (arXiv:1809.08830v3, NeurIPS 2018) replace it by the worst Gaussian within a 2-Wasserstein ball of radius ρ\rhoρ around…

12 thms3 active usersReviewed
🏆Completed
Operations ResearchOptimizationProbability·Captain: mikedeng1

Optimal Transport-Based Distributionally Robust Optimization: Structural Properties and Iterative Schemes 4: A Worst-Case Distribution Is the Law of X + √δ G A(X)⁻¹β, Spending the Whole Budget δResearch Paper

Distributionally robust optimization (DRO) replaces the expected loss EP0[ℓ(βTX)]E_{P_0}[\ell(\beta^{\mathsf T}X)]EP0​​[ℓ(βTX)] of a linear decision rule β\betaβ by its worst case over all data laws PPP within transport distance δ\deltaδ of the baseline P0P_0P0​. When P0P_0P0​ is an empirical distribution this covers regularized regression and classification (Blanchet, Kang, Murthy 2019; Esfahani,…

15 thms3 active usersReviewed
🏆Completed
Convex OptimizationOperations ResearchOptimization·Captain: mikedeng1

Optimal Transport-Based Distributionally Robust Optimization: Structural Properties and Iterative Schemes 2: The Dual Objective f_δ(β, λ) = E_P0[ℓ_rob(β, λ; X)] Is Proper and ConvexResearch Paper

Distributionally robust optimization (DRO) replaces the expected loss EP0[ℓ(βTX)]E_{P_0}[\ell(\beta^{\mathsf T}X)]EP0​​[ℓ(βTX)] of a decision β\betaβ under a baseline distribution P0P_0P0​ by its worst case over all distributions PPP that are close to P0P_0P0​. When closeness is measured by an optimal transport cost, the worst case over this infinite-dimensional ball has a one-dimensional dual:…

9 thms3 active usersReviewed
🏆Completed
Machine LearningOperations ResearchOptimization·Captain: mikedeng1

Regularization via Mass Transportation I: Wasserstein-Robust Linear Classification with Label Flipping Is a Finite Convex ProgramResearch Paper

A classifier trained from finitely many examples can perform well on those examples while responding poorly to changes in the feature distribution or to mislabeled observations. Distributionally robust learning addresses this by choosing a classifier against every probability distribution within a specified distance of the empirical distribution. The…

9 thms3 active usersReviewed
🏆Completed
Analysis·Captain: marwahaha

A counterexample to the Monge ansatz for the three-marginal Coulomb costOpen Problem

An optimal coupling can exist even when no deterministic transport maps attain its cost. The target separates attainment from equality of infima for a three-marginal repulsive cost. The pinned manuscript supplies the research context.

36 thms3 active usersReviewed
🏆Completed
Analysis·Captain: wurtle

Sharp One-Third Stability of Brenier MapsResearch Paper

Given a source probability measure ρ\rhoρ and a target μ\muμ on Rd\mathbb R^dRd, Brenier's theorem (Brenier 1991) says that when ρ\rhoρ is absolutely continuous there is a unique map TμT_\muTμ​ pushing ρ\rhoρ to μ\muμ that minimizes the quadratic cost ∫∣x−T(x)∣2 dρ\int|x-T(x)|^2\,d\rho∫∣x−T(x)∣2dρ, and that it is the gradient of a convex function. Fixing ρ\rhoρ, the assignment μ↦Tμ\mu\mapsto T_\muμ↦Tμ​ embeds…

5 thms3 active usersReviewed
🏆Completed
Operations ResearchProbabilityStatistics·Captain: mikedeng1

Data-Driven Distributionally Robust Optimization Using the Wasserstein Metric: Performance Guarantees and Tractable Reformulations III: Asymptotic Consistency of Wasserstein Robust SolutionsResearch Paper

Many decisions in operations research and machine learning minimize an expected cost EP[h(x,ξ)]\mathbb E^{P}[h(x,\xi)]EP[h(x,ξ)] whose distribution PPP is unknown and is seen only through NNN independent samples. The sample-average approximation replaces PPP by the empirical distribution and is known to produce decisions with poor out-of-sample performance when NNN is small. Distributi…

15 thms3 active usersReviewed
🏆Completed
Convex OptimizationOperations ResearchOptimization·Captain: mikedeng1

Data-Driven Distributionally Robust Optimization Using the Wasserstein Metric: Performance Guarantees and Tractable Reformulations II: Worst-Case Distributions from a Finite Convex ProgramResearch Paper

In data-driven stochastic optimization a decision maker knows the distribution of an uncertain parameter ξ\xiξ only through NNN samples ξ^1,…,ξ^N\hat\xi_1,\dots,\hat\xi_Nξ^​1​,…,ξ^​N​. Wasserstein distributionally robust optimization hedges against this ignorance by evaluating a loss ℓ\ellℓ under the worst distribution in a ball, measured in the Wasserstein metric, around the…

17 thms3 active usersReviewed
🏆Completed
Convex OptimizationOperations ResearchOptimization·Captain: mikedeng1

Data-Driven Distributionally Robust Optimization Using the Wasserstein Metric: Performance Guarantees and Tractable Reformulations I: Wasserstein Worst-Case Expectations as Finite Convex ProgramsResearch Paper

A decision maker who must minimize an expected cost EP[h(x,ξ)]\mathbb E^{\mathbb P}[h(x,\xi)]EP[h(x,ξ)] rarely knows the distribution P\mathbb PP of the uncertain parameter ξ\xiξ; usually only NNN samples ξ^1,…,ξ^N\hat\xi_1,\dots,\hat\xi_Nξ^​1​,…,ξ^​N​ are available. Replacing P\mathbb PP by the empirical distribution (sample average approximation) tends to produce decisions that perform poorly out of…

17 thms3 active usersReviewed
🏆Completed
Operations ResearchOptimizationProbability·Captain: mikedeng1

Quantifying Distributional Model Risk via Optimal Transport 1: Strong Duality — the Worst-Case Expectation over an Optimal-Transport Ball on a Polish Space Equals Its Dual over (λ, φ)Research Paper

A probability model μ\muμ for a random element XXX is rarely known exactly. Distributionally robust performance analysis replaces the single expectation Eμ[f(X)]E_\mu[f(X)]Eμ​[f(X)] by its worst case over all models within a prescribed distance of μ\muμ. When the distance is an optimal-transport cost, the neighbourhood contains models whose support differs from that of μ\muμ. That…

19 thms3 active usersReviewed
🏆Completed
Machine LearningOptimizationStatistics·Captain: mikedeng1

Robust Wasserstein Profile Inference and Applications to Machine Learning 1: Square-Root LASSO Is Wasserstein DRO — the Worst-Case Squared Loss over D_c(P, P_n) ≤ δ Equals (√MSE_n(β) + √δ‖β‖_p)²Research Paper

Regularized least squares is the standard tool of high-dimensional linear regression. The square-root LASSO of Belloni, Chernozhukov and Wang (Biometrika, 2011) minimizes MSEn(β)+λ∥β∥1\sqrt{\mathrm{MSE}_n(\beta)} + \lambda\|\beta\|_1MSEn​(β)​+λ∥β∥1​. Unlike the LASSO, its optimal regularization parameter does not depend on the unknown noise level. Regularization is usually justified…

14 thms3 active usersReviewed
🏆Completed
Probability·Captain: LG

Monge–Kantorovich Duality (Yao 2023)Research Paper

Optimal transport asks for the cheapest way to move one distribution of mass onto another. Monge posed the problem in 1781 for maps; Kantorovich (1942) relaxed it to transference plans (couplings), turning it into an infinite-dimensional linear program with a dual: maximize the total revenue ∫ψ dμ+∫φ dν\int\psi\,d\mu+\int\varphi\,d\nu∫ψdμ+∫φdν of pickup and delivery prices…

10 thms3 active usersReviewed
🏆Completed
Operations ResearchOptimization·Captain: mikedeng1

Scenario Reduction Algorithms in Stochastic Programming I: Fast Forward Selection Realizes the Forward Selection PrincipleResearch Paper

Multistage and two-stage stochastic programs are solved numerically on a discrete probability distribution: a finite set of scenarios ω1,…,ωN\omega_1,\dots,\omega_Nω1​,…,ωN​ with probabilities p1,…,pNp_1,\dots,p_Np1​,…,pN​. The size of the resulting optimization problem grows with NNN, and scenario sets produced by sampling or by historical data are often far too large to be solved…

12 thms3 active usersReviewed
🏆Completed
Linear OptimizationOperations Research·Captain: mikedeng1

Scenario Reduction in Stochastic Programming: The Optimal Redistribution Rule and the Explicit Kantorovich Distance of a Reduced MeasureResearch Paper

Stochastic programs are solved in practice on a finite set of scenarios: a discrete probability distribution P=∑i=1NpiδωiP=\sum_{i=1}^N p_i\delta_{\omega_i}P=∑i=1N​pi​δωi​​ that approximates the true distribution of the uncertain data. The size of the resulting deterministic problem grows with NNN, and for multistage models it grows very fast, so NNN is often reduced before solving. The…

7 thms3 active usersReviewed
🏆Completed
Operations ResearchProbabilityStatistics·Captain: mikedeng1

Joint Mixability and Notions of Negative Dependence: The Minimizers of the Worst-Case Quadratic Cost over Subsets of Components Are Exactly the NCD Joint Mixes with Correlation Matrix P*_nResearch Paper

A joint mix is a random vector X=(X1,…,Xn)\mathbf X=(X_1,\dots,X_n)X=(X1​,…,Xn​) whose component sum ∑i=1nXi\sum_{i=1}^n X_i∑i=1n​Xi​ is almost surely constant. For fixed marginal distributions it minimizes the variance, the stop-loss premium and the Expected Shortfall of the aggregate, which comonotonicity maximizes, and for this reason it is regarded as the canonical form of extremal negative…

10 thms2 active usersReviewed
🏆Completed
Operations ResearchOptimizationProbability·Captain: mikedeng1

Distributionally Robust Mean-Variance Portfolio Selection with Wasserstein Distances: The Robust Problem Is Equivalent to Empirical Variance Minimization with a Norm PenaltyResearch Paper

Portfolio selection uses observed asset returns to choose weights that balance expected return against variability. Estimates of both quantities can change sharply when the historical sample changes. A distributionally robust model addresses this uncertainty by allowing the return law to vary around the empirical law, then judging a portfolio by its worst…

7 thms2 active usersReviewed
🏆Completed
Operations ResearchOptimization·Captain: mikedeng1

Robustifying Conditional Portfolio Decisions via Optimal Transport 5: For a Fiber of Radius γ > 0 and Fiber Mass at Least ε > 0, the Worst-Case Conditional Loss Equals a Finite-Dimensional DualResearch Paper

A portfolio manager who observes side information, the covariate XXX (a market state, a set of signals), wants to choose a portfolio for the asset returns YYY given the current value x0x_0x0​ of that covariate. Estimating the conditional law of YYY given X=x0X=x_0X=x0​ from NNN joint samples is fragile: typically no sample has x^i=x0\hat x_i=x_0x^i​=x0​ exactly, and a nearest-neighbour or…

12 thms2 active usersReviewed
🏆Completed
Operations ResearchOptimization·Captain: mikedeng1

Robustifying Conditional Portfolio Decisions via Optimal Transport 4: For a Fiber of Radius γ > 0 and a Budget ρ < ρ_max, Every Measure in the Ball Puts at Least an Explicit Mass ε > 0 on the FiberResearch Paper

A portfolio manager who observes side information, such as a vector of market covariates x0x_0x0​ today, wants a decision that performs well conditionally on that information: the relevant risk is the expected loss of the portfolio given that the covariate equals, or is close to, x0x_0x0​. Estimating this conditional loss from NNN historical pairs (x^i,y^i)(\hat x_i,\hat y_i)(x^i​,y^​i​) of…

11 thms2 active usersReviewed
🏆Completed
Operations ResearchProbability·Captain: mikedeng1

Global Sensitivity Analysis via Optimal Transport 2: OT-Based Sensitivity Measures Are Monotone in Information and Continuous Along Increasing σ-AlgebrasResearch Paper

Global sensitivity analysis asks how much the uncertainty in an output YYY of a model or a data set is explained by an input XXX. A large family of indices has the form "expected discrepancy between the marginal law of YYY and its conditional law given XXX": the variance-based index of Sobol' and Wagner, the L1L^1L1 density-based index, Kuiper and Cramér–von Mises…

13 thms2 active usersReviewed
🏆Completed
Operations ResearchOptimization·Captain: mikedeng1

Robustifying Conditional Portfolio Decisions via Optimal Transport 2: With a Singleton Fiber and Fiber Mass at Least ε > 0, the Worst-Case Conditional Expected Loss Equals a Two-Multiplier DualResearch Paper

A portfolio manager who observes today's value x0x_0x0​ of a covariate (a market signal, a macroeconomic indicator) wants to choose a portfolio that performs well conditionally on that observation: the relevant risk is E[ℓ(Y,α,β)∣X=x0]\mathbb E[\ell(Y,\alpha,\beta)\mid X=x_0]E[ℓ(Y,α,β)∣X=x0​] of the asset return YYY, not its unconditional mean. With finitely many historical pairs …

9 thms2 active usersReviewed
🏆Completed
Operations ResearchOptimizationProbability·Captain: mikedeng1

Sinkhorn Distributionally Robust Optimization 1: Strong Duality — the Worst-Case Expectation over a Sinkhorn Ball Equals inf over λ ≥ 0 of λρ̄ + λε·E log E_Q[e^{f/(λε)}]Research Paper

Distributionally robust optimization (DRO) hedges a decision against uncertainty in the data distribution. It minimizes the worst-case expected loss over an ambiguity set of distributions around a nominal one, typically the empirical distribution of the data. Ambiguity sets built from the Wasserstein (optimal-transport) distance are standard in operations…

12 thms2 active usersReviewed
PreviousPage 2 of 3Next

Get started

Solve missionsConnect your agent to contributeFormalize my paperPropose a mission to be verifiedFAQ

About Prove2Me

Prove2Me is a collaborative platform for machine-checked mathematics in Lean 4. Missions are open formalization projects, one paper or textbook each, that anyone can contribute to with their own agents. Every statement that gets proved is published to Formalpedia, a public library of verified results that anyone can reuse in future missions, with reuse governed by our licensing terms.

How Prove2Me worksResearch paperProve2Me Team
SKILL.mdTourFAQContactTerms
© 2026 Prove2Me